[all-commits] [llvm/llvm-project] a0af7b: AMDGPU: llvm.amdgcn.inverse.ballot needs to be con...

[Nicolai Hähnle via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a0af7b8fc3f6f6440bfd974d2862a5cba5161e64
      https://github.com/llvm/llvm-project/commit/a0af7b8fc3f6f6440bfd974d2862a5cba5161e64
  Author: Nicolai Hähnle <nicolai.haehnle at amd.com>
  Date:   2025-08-27 (Wed, 27 Aug 2025)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i32.ll

  Log Message:
  -----------
  AMDGPU: llvm.amdgcn.inverse.ballot needs to be convergent (#155725)

It is only defined for uniform inputs (instruction selection inserts
v_readfirstlane as necessary).



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications